Nanocrowd Movie Search App for iPad is now available (and free!) in the Apple App Store

We've just launched our first iPad app, and it's available free in the Apple App Store.

Easy to use
Using the new Nanocrowd Movie Search app is easy -- enter the name of a movie you love and we'll suggest several channels that capture why other people enjoyed that movie. Pick the channel that matches your interest (and your mood) and then click on any of the movies in the list to get more information or to watch it on your iPad.

Here's a short demo/how-to video (try fullscreen and HD for the best view).



To watch all the movies in our application, you'll need an iPad and a Netflix streaming account.

We know WHY people like things
The new app is built with Reaction Mapping® technology, which we developed to analyze viewer comments about movies. These comments capture people's reactions to movies, and analyzing them allows Nanocrowd to understand not only what movies people enjoy, but also why they enjoy them. Understanding why is crucial because movies evoke a variety of feelings and emotions that are complex and can’t be captured by ratings or rental histories. More about our Reaction Mapping tech can be found at a previous blog post.

Watching movies instantly is a click away
Every movie in the Nanocrowd movie search app is available to watch instantly on an iPad from sites like Netflix, YouTube, and Internet Archive (with more sites planned).

Of course, we want to do lots more than just help you search for a movie, so we're already working on the next update to our app, where you'll be able to save the channels you like and then we'll automatically alert you if there are new movies available in your favorite channels. If you'd like an invitation to become a beta tester for this update, you can click on the links in the search app or send us an email now.

I hope you have fun with our new app!

posted by Roderic March

Nanocrowd demo at APPNATIONIII

Nanocrowd was selected to demo at the APPNATIONIII conference on Wednesday 11/30/2011 in San Francisco. APPNATION is an executive conference and exposition focused on the consumer applications economy. Over 3000 developers, carriers, product/service providers, buyers and investors attended previous APPNATION conference and expos. We are excited to be going this year, because their theme is "Show me the money," and that is a core issue facing all mobile app developers today.

No, that's not me at the demo pod ;-)

We'll be demoing our search.nanocrowd.com webapp as well as previewing our upcoming myChannels application. I hope you can come by and see me or our CEO, Roderic March at our demo pod in the Mobile Monday Village.

posted by Laura Torres

Great time at SenchaCon2011

Doug Millasich and I wandered down to Austin this week to speak at SenchaCon2011, Sencha's annual US developer conference. It was a great conference, and not only did we get the latest news about Sencha and their products, we also met lots of other folks who are building their mobile applications with Sencha Touch.

Sencha looks like it's going to continue to be a great platform with lots to offer, and we remain pleased with our decision to build our products using their app framework. We're looking forward to enhancing upcoming products with the new features and improvements coming with Sencha Touch 2.0.

We also enjoyed what a great music-town Austin is. We wandered the street and hear some fabulous music at the Dia de los Muertes festival downtown, and Sencha invited all the conference attendees to Stubbs for barbecue and live music by Black Joe Lewis and The Honeybears. It seemed like there was live music at every corner and in every restaurant. What a delight.

posted by Roderic March

Nanocrowd launches iPad movie search app

Before Nanocrowd
It’s Friday night after a long week. You just want to grab something to drink, sit down, and watch a movie. Nothing too deep. Nothing violent. Maybe a comedy. And so the thought process continues as you get online and start searching for something to watch. Simple. Then it happens. 10 minutes goes by, then 20. Frustrated you think, “There’s nothing to watch!” On to plan B: Checking e-mail, trolling the web, World of Warcraft, scrolling through your TV channels.


After Nanocrowd
Picking up your shiny new iPad, you point your browser to search.nanocrowd.com and type in “The Proposal” – a movie you loved. “Chemistry Sweet Adorable” sounds like what you’re in the mood for. You see a channel full of movies which include some of your all-time favorites. But then you notice one you haven't seen “One Fine Day” – Hmm… something you may not have thought of, but it sounds good. You watch the trailer and decide to watch it instantly. Nanocrowd launches the movie, available from Netflix, and off you go to enjoy your movie. No login. No hassle.

Available today
If you have an iPad and love to watch movies but hate the hassle of searching and finding one to watch, pull out your iPad, open Safari, and browse to our new movie-search application (search.nanocrowd.com). We currently link to movies from Netflix and YouTube, and we're working on linking to more sources.

At Nanocrowd, we actually understand why people like movies (for more details, see our earlier blog post) and because we understand why, we can make quick and accurate movie recommendations without the need for you to give us pages of profile data or provide us with movie ratings.

We know that on Friday night, after a long week, you’d rather be watching a movie than spending time looking for one. Try it out and tell us what you think.

posted by Roderic March

Nanocrowd at Mobile Monday event "HTML5: The next trend for mobile"

On Monday, August 8 Mobile Monday Silicon Valley is focusing their monthly meeting on HTML5 and its role in mobile computing. They have invited us to join several other entrepreneurs and experts to discuss how HTML5 is influencing our design and development plans.

In addition to a panel discussion and Q&A, Nanocrowd will give a sneak-peek demo of our upcoming HTML5 webapp designed for the iPad. Our new application uses the same Reaction Mapping(r) technology that drives our website, but turns it into a personalized channel application for watching movies.

Mobile Monday is a great group of tech professionals who get together to discuss important issues for mobile computing. This meeting will be at the Computer History Museum in Mountain View, CA (register here). It's free -- so come see what we've been up to. Our Lead Developer, Doug Millasich will be there too, so I hope you can make it!

posted by Roderic March

Movie Genres and Taste Maps (and why they remind me of choosing Waffles or Eggs Benedict for breakfast)

A few days ago, I met a friend for breakfast at my favorite diner. While thinking about whether to order Belgian Waffles or Eggs Benedict, I suddenly had a flashback to elementary school science class. It was that lesson about the taste buds! You know – the taste map of your tongue with the salt, sweet, sour, bitter categories. I was confused by that map in elementary school and was still confused as I stared at the menu. I wasn't going to choose waffles or eggs just because one was sweet and one was salty.

It occurred to me that selecting a movie is a lot like deciding what you're going to eat for breakfast.

For me, genres like action, drama, or romance don't capture my movie taste any better than sweet and salty captures the difference between waffles and eggs Benedict. Movies are complex, and when I am trying to decide what movie to watch I am usually thinking something like: "Do I want an uplifting, happy-ending, formulaic Hollywood-type of movie or a car-chasing, high-energy thriller?"

At Nanocrowd, we've developed nanogenre™ movie categories – a method of describing movies in much more detail than simply drama or romance (you can find more information about our technology here). With nanogenre categories, people can choose movies the same way they choose breakfast. A "gangster, flashy, violence" movie or a "gripping, morality, fascinating" one?

Our website currently uses nanogenre categories for a one-at-a-time movie recommendation engine, but we are working on a new way to use these fine-tuned genres to create individual "taste maps" and suggest lots of movies all at once that that are automatically tailored to your taste.

Building Your Taste Map
To build your taste map, we begin with a list of the movies you have watched. Then we look into our collection of thousands and thousands of nanogenre categories and add a bunch of math to figure out why you watched those movies and which categories are right for you.

The result is a physical map of your taste, showing what types of movies you like and how they "cluster" around each other. Here is an example of "Rick's" taste map (the name has been changed to protect the innocent).

Click on the image (or here) to learn more.

For illustration, we circled the nanogenre categories that fall into more traditional genres like War and Romantic drama. The power of having Rick's taste map is that instead of just noticing that Rick likes Sci-fi action and Romantic comedies, we have broken those categories into much more specific groups of movies with descriptions like:

robbery, coolness, mastermind
future, humans, thought-provoking
comedy, touching, delight

Using these nanogenre categories, we can find lots of movies that are perfect for Rick.

At Nanocrowd, we are just starting to test an application that figures out viewers' taste maps and recommends collections of movies based on those maps. If you are feeling courageous and would like to join our Alpha testing program, let us know.

As for breakfast, I chose the waffles.

posted by Roderic March

A simple way to test your music recommendation engine (the results suggest that Pandora understands why people like songs)

I spend a lot of time thinking about recommendation engines and evaluating results, so I thought I could suggest a simple test that you can do yourself in a minute or two. Here it is:

Simple test for music recommendation sites (Do try this at home!) For one of your favorite artists, think of two songs that are very different. You may enjoy them both (or not), but they are so different that you would play each at different times. One for dancing. One for a quiet evening. Perhaps one to soothe your broken heart. Go to your music recommendation site and ask them to recommend songs for each. Check the results to see if they could tell the difference between the two songs.

For example, I picked two songs by Lady Gaga that are both popular hits, but are very different:

Lady Gaga Eh Eh, (Nothing Else I can Say) is a bouncy, pure-pop lark Bad Romance is harder, with R&B influences, and oozing sensuality

I tested them out at 3 sites: Pandora, Amazon, and Last.fm. Ignoring songs by the same artist, here are the top two recommendations I got back from Pandora for each of my songs:

Lady Gaga Songs I like	Pandora recommends
Eh Eh, (Nothing Else I can Say) a bouncy, pure-pop lark	Miley Cyrus Party in the USA is as pure pop as pop can be.
	Shakira She Wolf did I say pure pop yet?
Bad Romance R&B influences and oozing sensuality	Beyonce Sweet Dreams fun R&B match
	Taio Cruz Break Your Heart not much like Miley Cyrus!

Pandora

You can tell immediately that Pandora recognized the difference between these two songs. I admit that I'm not that fond of Eh Eh, because it is such pure pop, and Pandora's recommendations are in that same vein. However, I can't get enough of Bad Romance, and both of the songs Pandora recommended are now on my playlist.

I asked Last.fm and Amazon to recommend songs based on the same two songs, and you can compare their results to Pandora's below:

Lady Gaga Eh-Eh Pandora Miley Cyrus Party in the USA Shakira She Wolf Amazon Katy Perry Teenage Dream Ke$ha TiK ToK Last.fm Ke$ha Hungover Britney Spears Radar

Amazon

Amazon bases their recommendations on purchase history ("people who bought this also bought"). You can see that they did a good job of finding pop songs to match Eh Eh.

Last.fm

Last.fm uses preference matching to make their recommendations ("people who listen to this also like"), and their matches were almost identical to Amazon's. Again I got two pop artists' songs as a match to Eh Eh (although Last.fm did swap out Katy Perry and replaced her with Britney Spears -- not sure what that means).

Now let's compare how the 3 sites did with Bad Romance:

Lady Gaga Bad Romance Pandora Beyonce Sweet Dreams Taio Cruz Break Your Heart Amazon Ke$ha TiK ToK Katy Perry Hot N Cold Last.fm Ke$ha TiK ToK Britney Spears 3

Pandora's recommendations for Bad Romance were very different from the songs they suggested for Eh Eh, accurately reflecting the difference between the two songs.

Even though they didn't do as good a job as Pandora, to their credit, both Amazon and Last.fm recommended pop songs for Bad Romance by the same artists they recommended for Eh Eh. In fact, Amazon recommended the exact same song:TiK ToK for both. I like TiK ToK, and I thought it was a great match for Eh Eh, but even if I squint and tip my head, I have trouble considering it a good match for Bad Romance.

Perhaps Amazon and Last.fm are really recommending artists that are similar to artists you like. Katy Perry and Ke$ha are good artist suggestions for someone who likes Lady Gaga (in fact, Teenage Dream is one of my favorite songs), but if I want to base my listening on the unique qualities of either Eh Eh or Bad Romance, neither Amazon nor Last.fm recognized the difference between these two songs.

LeAnn Rimes

I did the test again with two songs by LeAnn Rimes and once again Pandora did much better. The first song is Blue, a lovely "old-school" country ballad intended for Patsy Cline in the early 1960s. The second, Can't Fight the Moonlight is a pop song that wasn't even officially released on country radio.

For Blue, all three sites recommended country music (who knew that Kid Rock did such a beautiful country ballad?).

LeAnn Rimes Blue Pandora Kid Rock Picture Pam Tillis Cleopatra, Queen of Denial Amazon Patsy Cline Crazy Ernest Tubb Waltz Across Texas Last.fm Reba McEntire Is There Life Out There? Trisha Yearwood She's In Love With the Boy

When I asked for recommendations similar to Can't Fight The Moonlight, Pandora clearly recognized how different that song was from Blue. Both songs they recommended are pop songs by pop artists.

By contrast, the other two sites recommended country music for all.

LeAnn Rimes Can't Fight the Moonlight Pandora Britney Spears Oops, I did it Again Jennifer Lopez Waiting for Tonight Amazon Reba McEntire Because of You Tim McGraw Live Like You were Dying Last.fm Faith Hill This Kiss Shania Twain That Don't Impress me Much

To their credit, both Amazon and Last.fm suggested more traditional country matches for Blue and more new-country matches for Can't Fight the Moonlight.

Why are Pandora's recommendations so much better?

Before making any recommendations, Pandora has already analyzed each of my songs using their Music Genome Project. This analysis unearthed the core elements of the songs and helped Pandora understand why people like each song so they can then recommend similar songs.

Understanding why is crucial, because music is complex and people like songs for different reasons. Pandora understands the subtle elements of the music I like and makes accurate recommendations. These subtle differences in why people like specific songs are not easily captured by ratings or purchase histories.

Pandora's approach makes them a great music discovery tool. I am frequently both surprised and delighted by the songs they recommend on my Bad Romance station. Most of the new artists I enjoy today were discovered by listening to Pandora.

posted by Roderic March